Reverse dispersion entropy

[kahaaga]

This PR introduces the reverse dispersion entropy (RDE) (Li et al., 2019).

Implements

• ReverseDispersion <: ProbabilitiesEstimator, which can only be used for probability computations, not entropy computations.
• The entropy_reverse_dispersion(x::AbstractVector) function, which computes the reverse dispersion entropy for scalar-valued input.

Reviewing/merging

This should not be merged until after #80 is finished, and the API change discussed in #81 is done. However, it follows the new api discussed in #81, so can be reviewed before that.

I'm keeping it as a draft to remind myself to revisit this after the main api has changed.

References

Li, Y., Gao, X., & Wang, L. (2019). Reverse dispersion entropy: a new complexity measure for sensor signal. Sensors, 19(23), 5203.

[codecov]

Codecov Report

Merging #83 (c86980a) into main (875cfbe) will decrease coverage by 0.06%.
The diff coverage is 95.45%.

@@            Coverage Diff             @@
##             main      #83      +/-   ##
==========================================
- Coverage   79.23%   79.17%   -0.07%     
==========================================
  Files          22       23       +1     
  Lines         631      653      +22     
==========================================
+ Hits          500      517      +17     
- Misses        131      136       +5     

Impacted Files	Coverage Δ
src/dispersion/reverse_dispersion_entropy.jl	95.45% <95.45%> (ø)
src/binning_based/rectangular/TransferOperator.jl	72.13% <0.00%> (-3.28%)	⬇️

📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more

[kahaaga]

I'm closing this in favor of #96